A plot development method, system, terminal and storage medium

Abstract

The present application relates to the technical field of plot development, and discloses a plot development method, system, terminal and storage medium, the method comprising: structuring an initial plot description text into a narrative graph to obtain structured script data, and constructing a character profile by reducing character personality and background characteristics; constructing a chapter container according to chapter composition logic and assigning scene definition information to generate development structure data; configuring a plot development and deriving a driving control rule; based on the development structure data, performing semantic behavior deduction on the character profile to obtain a realistic dialogue text, and driving instance the driving control rule and the chapter content template called by the user to obtain chapter expansion data; updating the structured script data using the chapter expansion data, and performing space-time narrative fusion on the updated structured script data and the realistic dialogue text to obtain a complete narrative structure; the present application can improve the efficiency of plot development.

Description

Technical Field

[0001] This invention relates to the field of storytelling technology, and in particular to a storytelling method, system, terminal, and storage medium. Background Technology

[0002] In the current process of plot development, the processing of the initial plot description text lacks a systematic and structured approach, making it difficult to effectively sort out the narrative logic, character relationships, and scene connections in the text. This results in disorganized script data, which cannot provide clear logical support for subsequent performances, and thus affects the coherence and rationality of the plot progression.

[0003] In traditional storytelling, character development and plot development are disconnected, lacking precise definition and deep integration of character personality and background characteristics. Furthermore, plot configuration and content expansion rely heavily on human experience, failing to achieve dynamic adaptation to character traits and scene requirements. This results in a lack of realism and personalization in the performed story, leading to low overall performance efficiency. Therefore, improving the efficiency of storytelling has become an urgent problem to be solved. Summary of the Invention

[0004] This disclosure provides a method, system, terminal, and storage medium for storytelling.

[0005] Firstly, this disclosure provides a method for storytelling, including:

[0006] S1. Perform narrative graph structuring on the initial plot description text to obtain the structured script data of the initial plot description text;

[0007] S2. Semantically reduce the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data;

[0008] S3. Based on the chapter composition logic of the structured script data, construct a chapter container for the structured script data, and allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data.

[0009] S4. Based on the plot development requirements in the deductive structure data, configure the plot direction for the chapter container, and derive the control logic from the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data.

[0010] S5. Based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain the realistic dialogue text of the character profile, and the advancement control rules and the chapter content template called by the user are instantiated in a driven manner to obtain the chapter extension data of the structured script data.

[0011] S6. Update the structured script data using the chapter extension data, and perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

[0012] In a preferred embodiment, the step of structuring the initial plot description text into a narrative graph to obtain structured script data of the initial plot description text includes:

[0013] Multimodal semantic parsing is performed on the initial plot description text to obtain the first text analysis product of the initial plot description text;

[0014] Identify the syntactic dependency relationships between lexical items in the first text analysis product, and construct the syntactic dependency relationships in a structured manner to obtain the second text analysis product of the initial plot description text;

[0015] Using the action descriptors, agent roles, and patient roles in the second text analysis product as nodes and the syntactic dependency relations as edges, an initial narrative graph structure of the initial plot description text is constructed.

[0016] Semantic role annotation is performed on the nodes in the initial narrative graph structure to obtain the preliminary structured data of the nodes;

[0017] Logical link closure is performed on the preliminary structured data to obtain the final narrative graph of the initial plot description text;

[0018] The final narrative graph is serialized and encapsulated to obtain the structured script data of the initial plot description text.

[0019] In a preferred embodiment, the step of semantically reducing the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data includes:

[0020] Extract the personality trait description text and background trait description text of the character definition information from the structured script data;

[0021] Based on a pre-defined public personality classification system, the personality trait description text is mapped to a standardized personality tag set, and the standardized personality tag set is integrated through multi-dimensional clustering to generate a personality semantic reduction product of the personality trait description text.

[0022] Relation topology extraction is performed on the background feature description text to obtain the background semantic reduction product of the background feature description text;

[0023] The personality semantic reduction product and the background semantic reduction product are semantically fused to obtain the character profile of the structured script data.

[0024] In a preferred embodiment, the step of constructing a chapter container for the structured script data based on the chapter composition logic of the structured script data, and allocating scene definition information from the structured script data to the chapter container to generate the deductive structure data of the structured script data, includes:

[0025] Based on the narrative unit segmentation rules and hierarchical constraints contained in the structured script data, the chapter skeleton framework of the structured script data is extracted to obtain the logical empty container of the structured script data.

[0026] Based on the position and context dependency of the logical empty container in the chapter skeleton framework, the logical empty container is bound to a context to obtain the chapter container of the logical empty container;

[0027] Tensor synthesis is performed on the scene definition information in the structured script data to obtain the scenario feature vector of the scene definition information;

[0028] The chapter container is vectorized into context to obtain the intent feature vector of the chapter container;

[0029] The semantic similarity between the context feature vector and the intent feature vector is calculated to obtain the association mapping result of the structured script data. The calculation formula for the association mapping result is as follows:

[0030] ;

[0031] In the formula, For the first The scenario definition information and the first The mapping results between chapter containers For the first A scenario feature vector that defines the information of a scenario. For the first The intentional feature vector of each chapter container. This is the transpose of the intention feature vector. For the pre-defined narrative logic weight matrix, For the first The scene definition information and the first The logical distance between the chapter containers in the narrative order The preset position distance penalty coefficient;

[0032] Based on the association mapping result, the chapter container is synchronized in state, and the synchronized chapter container and the scene definition information are encapsulated in a structure to obtain the deductive structure data of the structured script data.

[0033] In a preferred embodiment, configuring plot directions for the chapter container based on the plot development requirements in the deductive structure data, and deriving control logic from the plot directions and preset chapter content templates to obtain the progression control rules for the deductive structure data, includes:

[0034] Extract the state attributes of the chapter containers and the scene definition information from the deductive structure data to obtain the plot development requirement description of the deductive structure data;

[0035] The plot development requirements are matched with the historical plot pattern library to obtain the preliminary plot direction configuration of the deductive structure data;

[0036] Based on the initial plot development configuration, the preset chapter content templates are associated and mapped to obtain the structured narrative templates of the chapter content templates;

[0037] Based on the scene definition information associated with the chapter container, a narrative manifold is constructed on the structured narrative template to obtain the optimized plot direction of the initial plot direction configuration;

[0038] Based on the optimized plot development, the chapter content template is fused according to rules to obtain the control logic of the chapter content template;

[0039] Based on the order of the chapter containers in the deductive structure data, the control logic is integrated by logical link chaining to obtain the advancement control rules of the deductive structure data.

[0040] In a preferred embodiment, based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain realistic dialogue text of the character profile. Then, the progression control rules and user-invoked chapter content templates are instantiated in a driven manner to obtain chapter extension data of the structured script data, including:

[0041] Based on the scene definition information and plot development associated with the current chapter container in the deductive structure data, context behavior reasoning is performed on the semantic reduction product of the character profile to obtain the character subtext sequence of the structured script data.

[0042] Based on the character's subtext sequence, a dialogue manifold is constructed for the event logic in the plot development to obtain the simulated dialogue text of the structured script data;

[0043] The chapter content template called by the user and the propagation control rules are deconstructed to obtain the driving parameters of the propagation control rules;

[0044] Based on the driving parameters, dynamic content injection is performed on the chapter content template called by the user to obtain the template after the structured script data is filled.

[0045] Based on the state transition path in the propulsion control rules, the narrative logic of the filled template is closed to obtain the preliminary chapter expansion data of the filled template;

[0046] The initial chapter extension data is aligned for context consistency to obtain the chapter extension data of the structured script data.

[0047] In a preferred embodiment, updating the structured script data using the chapter extension data and then performing spatiotemporal narrative fusion of the updated structured script data with the simulated dialogue text to obtain the complete narrative structure of the structured script data includes:

[0048] Based on the chapter extension data, the structured script data is versioned and supplemented to obtain the updated structured script data.

[0049] Based on the spatiotemporal attributes of the scene in the updated structured script data, the simulated dialogue text is spatiotemporally bound to the context to obtain the spatiotemporally anchored dialogue text.

[0050] Based on the spatiotemporally anchored dialogue text, narrative thread stitching is performed on the updated structured script data to obtain a preliminary narrative fusion of the updated structured script data;

[0051] Narrative topology optimization is performed on the preliminary narrative fusion to obtain the complete narrative structure of the structured script data.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. This invention structures the initial plot description text into a narrative graph, systematically sorts out the narrative logic, character relationships and scene associations, and forms standardized structured script data. At the same time, it semantically regulates the character personality and background characteristics, and constructs accurate and complete character profiles, providing solid data support for plot performance and ensuring the coherence of plot development and the consistency of character shaping.

[0054] 2. This invention generates deductive structure data by constructing logic according to chapters, configures the direction and derives the advancement control rules according to plot requirements, derives realistic dialogue text based on character profiles, realizes chapter content-driven instantiation expansion, and forms a complete narrative structure through spatiotemporal narrative fusion, thereby improving the realism and personalization of the plot performance, simplifying the performance process, and significantly improving the overall efficiency and quality of the plot performance. Attached Figure Description

[0055] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0056] Figure 1 The flowchart of a plot interpretation method according to Embodiment 1 of the present invention is shown;

[0057] Figure 2 This diagram shows a functional module diagram of a story interpretation system according to Embodiment 2 of the present invention;

[0058] Figure 3 The diagram shows the structural composition of a terminal implementing the storytelling method according to Embodiment 3 of the present invention. Detailed Implementation

[0059] To enable those skilled in the art to better understand the technical solutions of this disclosure, and to fully understand and implement the process of how this disclosure applies technical means to solve technical problems and achieve corresponding technical effects, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, not all embodiments. The embodiments of this disclosure and the various features within them can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort should fall within the protection scope of this disclosure.

[0060] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0061] Example 1

[0062] Figure 1 This is a flowchart illustrating a storytelling method provided in an embodiment of this disclosure. Figure 1 As shown, a smart device control method includes:

[0063] S1. Perform narrative graph structuring on the initial plot description text to obtain the structured script data of the initial plot description text;

[0064] In this embodiment of the invention, the step of structuring the initial plot description text into a narrative graph to obtain structured script data of the initial plot description text includes:

[0065] Multimodal semantic parsing is performed on the initial plot description text to obtain the first text analysis product of the initial plot description text;

[0066] Identify the syntactic dependency relationships between lexical items in the first text analysis product, and construct the syntactic dependency relationships in a structured manner to obtain the second text analysis product of the initial plot description text;

[0067] Using the action descriptors, agent roles, and patient roles in the second text analysis product as nodes and the syntactic dependency relations as edges, an initial narrative graph structure of the initial plot description text is constructed.

[0068] Semantic role annotation is performed on the nodes in the initial narrative graph structure to obtain the preliminary structured data of the nodes;

[0069] Logical link closure is performed on the preliminary structured data to obtain the final narrative graph of the initial plot description text;

[0070] The final narrative graph is serialized and encapsulated to obtain the structured script data of the initial plot description text.

[0071] The initial plot description text is broken down, and basic language units such as words, phrases, and sentences are extracted. The semantic connotation, grammatical function, and emotional tendency of each language unit are analyzed. At the same time, multi-dimensional information such as scene description, action pointing, and character association are identified in the text. The semantic, grammatical, emotional, scene, and character information obtained from these analyses are systematically integrated to form a set containing the core elements of the text and various related information. This set is the first text analysis product of the initial plot description text.

[0072] Each lexical item in the first text analysis product is analyzed one by one to clarify the grammatical function of each lexical item in the sentence. The syntactic dependency relationships between the lexical items, such as subject-verb-verb-object-modifier-complement and coordinate, are determined. These syntactic dependency relationships are presented in a hierarchical structure. A clear association framework is constructed according to the grammatical structure hierarchy of subject-verb-object-adjective-adverb-complement, so that the dependency object and dependency type of each lexical item are clear at a glance. This association framework is the second text analysis product of the initial plot description text.

[0073] From the second text analysis product, action descriptors representing specific behaviors and the agent and patient roles that perform the actions are selected. Each action descriptor, agent, and patient role is treated as an independent node. The syntactic dependencies between previously identified lexical items are used as edges connecting the nodes. According to the actual association between action descriptors and agents, agents and patients, and action descriptors and patients, all nodes are connected by corresponding edges to form a network structure that reflects the narrative logic of the text. This network structure is the initial narrative graph structure of the initial plot description text.

[0074] For each node in the initial narrative graph structure, based on its semantic context in the text and its relationship with other nodes, the node is labeled with a corresponding semantic role, clarifying that each node represents an action executor, action receiver, action itself, time adverbial, place adverbial, etc. All nodes with labeled semantic roles and their edges are organized to form a standardized and orderly structured data set, which is the preliminary structured data of the nodes.

[0075] Examine the logical relationships between nodes in the preliminary structured data to check for any logical breaks or incomplete connections. For nodes lacking necessary connections, supplement them with reasonable logical relationships to form a coherent logical chain between various nodes such as action descriptors, agents, and patients. This ensures that the entire narrative logic is complete and closed-loop. The narrative diagram after logical refinement is the final narrative diagram of the initial plot description text.

[0076] According to the preset standardized data format, all content such as node information, edge association information, semantic role annotation information, etc. in the final narrative graph are arranged in an orderly manner and transformed into a linear data form that can be stored, transmitted, and processed later. The linear data is then encapsulated, and the start and end markers of the data and the separation rules of each part of the data are clearly defined. The encapsulated linear data is the structured script data of the initial plot description text.

[0077] The beneficial effects are that through multi-step text analysis, structure construction, and data processing, the scattered initial plot description text is transformed into structured script data with clear logic and standardized structure. The core elements and relationships such as semantics, grammar, character actions, etc. in the text are systematically sorted out, providing accurate and complete basic data support for subsequent plot performance stages such as character profile construction and performance structure generation, effectively ensuring the coherence and logic of the plot performance.

[0078] S2. Semantically reduce the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data;

[0079] In this embodiment of the invention, the step of semantically reducing the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data includes:

[0080] Extract the personality trait description text and background trait description text of the character definition information from the structured script data;

[0081] Based on a pre-defined public personality classification system, the personality trait description text is mapped to a standardized personality tag set, and the standardized personality tag set is integrated through multi-dimensional clustering to generate a personality semantic reduction product of the personality trait description text.

[0082] Relation topology extraction is performed on the background feature description text to obtain the background semantic reduction product of the background feature description text;

[0083] The personality semantic reduction product and the background semantic reduction product are semantically fused to obtain the character profile of the structured script data.

[0084] The text paragraphs containing character definition information are located in the structured script data. Sentence by sentence, the content describing the character's personality tendencies, such as attitude towards people, way of expressing emotions, and characteristics of doing things, are filtered out. At the same time, the content describing the character's background, growth experience, interpersonal relationships, social status, etc. are extracted. The filtered personality-related texts are integrated into personality trait description texts, and the extracted background-related texts are integrated into background trait description texts.

[0085] The pre-defined public personality classification system includes standardized personality categories such as cheerful, introverted, persevering, timid, calm, impatient, open-minded, and narrow-minded. Each piece of content in the personality trait description text is semantically compared with the categories in this classification system. The standardized category with the highest semantic matching degree is used as the tag for the corresponding content. All tags are collected to form a standardized personality tag set. The tag set is then classified and integrated according to multiple dimensions such as emotional stability, social initiative, and decisiveness. Tags with similar semantics under the same dimension are merged to form a set that can comprehensively summarize the core traits of the character's personality. This set is the personality semantic specification product of the personality trait description text.

[0086] The background feature description text is analyzed sentence by sentence to extract core elements, including family relationships, career identity, educational background, key life events, and interpersonal networks. The logical connections between these core elements are then analyzed, such as the influence of family relationships on career choices and the changes in life attitudes caused by key events. A network-like relational topology is constructed with core elements as nodes and logical connections as edges, clearly presenting the internal connections and influence paths of each background element. This topology is the background semantic specification product of the background feature description text.

[0087] By matching the character traits embodied in the personality semantic specification product with the background elements and relationships presented in the background semantic specification product, the background root causes of personality traits are analyzed, such as introversion caused by lack of companionship during growth. At the same time, the constraints and influences of background elements on personality expression are clarified, such as workplace experience making a resolute personality more flexible. This interrelated personality and background information is systematically integrated to form a complete set of data containing the background origins of the character's core personality traits and the interaction logic between personality and background. This data is the character profile of the structured script data.

[0088] The beneficial effects are that by accurately extracting the character's personality and background features from the text, semantic reduction is achieved based on a standardized classification system and relational topology extraction, and the character profile constructed through semantic fusion can comprehensively and accurately present the character's core traits and internal logic. This provides a solid foundation for subsequent semantic behavior deduction and realistic dialogue text generation, ensuring the consistency and rationality of the character's behavior and dialogue in the plot.

[0089] S3. Based on the chapter composition logic of the structured script data, construct a chapter container for the structured script data, and allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data.

[0090] In this embodiment of the invention, the step of constructing a chapter container for the structured script data based on the chapter composition logic of the structured script data, and allocating scene definition information from the structured script data to the chapter container to generate the deductive structure data of the structured script data, includes:

[0091] Based on the narrative unit segmentation rules and hierarchical constraints contained in the structured script data, the chapter skeleton framework of the structured script data is extracted to obtain the logical empty container of the structured script data.

[0092] Based on the position and context dependency of the logical empty container in the chapter skeleton framework, the logical empty container is bound to a context to obtain the chapter container of the logical empty container;

[0093] Tensor synthesis is performed on the scene definition information in the structured script data to obtain the scenario feature vector of the scene definition information;

[0094] The chapter container is vectorized into context to obtain the intent feature vector of the chapter container;

[0095] The semantic similarity between the context feature vector and the intent feature vector is calculated to obtain the association mapping result of the structured script data. The calculation formula for the association mapping result is as follows:

[0096] ;

[0097] In the formula, For the first The scenario definition information and the first The mapping results between chapter containers For the first A scenario feature vector that defines the information of a scenario. For the first The intentional feature vector of each chapter container. This is the transpose of the intention feature vector. For the pre-defined narrative logic weight matrix, For the first The scene definition information and the first The logical distance between the chapter containers in the narrative order The preset position distance penalty coefficient;

[0098] Based on the association mapping result, the chapter container is synchronized in state, and the synchronized chapter container and the scene definition information are encapsulated in a structure to obtain the deductive structure data of the structured script data.

[0099] Based on the narrative unit segmentation rules clearly defined in the structured script data, these rules divide independent narrative segments according to the core criteria of plot integrity, time span, and scene transformation. At the same time, they follow the hierarchical constraints of the subordinate relationship between chapters and sections and the logical progression requirements between chapters. By sorting out the overall plot framework from the structured script data, the core functions of each chapter and the connection between them are clarified, forming a framework system that only contains the chapter structure logic without filling in specific content. This framework system is the logical empty container of the structured script data.

[0100] Clearly define the position of each logical empty container within the chapter skeleton framework, analyze its connection with previous chapters, its foreshadowing relationship with subsequent chapters, and its parallel relationship with chapters at the same level. Bind these contextual dependencies to the logical empty containers, determine the narrative intent that each logical empty container should carry in the corresponding stage of plot development, and give the logical empty containers a clear contextual orientation. The bound logical empty containers are the chapter containers of the logical empty containers.

[0101] Extracting the first from the structured script data The core elements of scene definition information include scene location, time, background, atmosphere, tone, characters, interaction, and preconditions. Each core element is transformed into quantifiable feature information. These feature information are arranged and combined according to a preset dimensional order. By integrating multi-dimensional feature information, a vector form that can comprehensively represent the core attributes of the scene is formed. This vector is the first... Each scenario defines a contextual feature vector.

[0102] Analysis of the first The narrative positioning of each chapter container within the overall plot is defined, clarifying its plot progression goals, information delivery objectives, and functional coordination requirements with other chapters. This contextual information is broken down into multiple quantifiable contextual elements, which are then organized and transformed according to a unified dimensional standard to form a vector form that accurately reflects the narrative intent of the chapter container. This vector is the first... The intention feature vector of each chapter container is obtained by transposing the rows and columns of the intention feature vector while keeping the quantitative information of each contextual element in the vector unchanged and only changing the presentation arrangement of the information.

[0103] The narrative logic weight matrix, pre-set according to common narrative rules and scene adaptation patterns in the plot, is retrieved. The values ​​in this matrix are used to adjust the influence of different dimensional features in the association matching. Simultaneously, the weight matrix is ​​calculated according to the arrangement order of the chapter containers in the chapter skeleton framework. The narrative node corresponding to the scene definition information and the first scene definition information The number of intervals between each chapter container in this order is the logical distance between them in the narrative order. A pre-set fixed value is used as the positional distance penalty coefficient to adjust the influence of the logical positional distance on the association mapping result. Then, the first... The scenario feature vector of the first scene definition information is multiplied by the narrative logic weight matrix, and then the result is multiplied by the first scene definition information. Multiplying the transposes of the intention feature vectors of each chapter container yields a numerator reflecting the degree of semantic association between the two. Simultaneously, the sum of the products of 1, the positional distance penalty coefficient, and the logical positional distance is calculated as the denominator. Finally, the numerator is divided by the denominator to obtain a comprehensive value that takes into account both semantic fit and narrative positional association. This comprehensive value is the association mapping result of the structured script data.

[0104] Based on the degree of fit between the scenario feature vector and the intent feature vector in the association mapping results, the attribute parameters of the chapter container are adjusted to ensure that they are consistent with the corresponding scene definition information in terms of narrative logic, thus completing the state synchronization of the chapter container. Subsequently, the state-synchronized chapter container is integrated with the corresponding scene definition information and encapsulated into a complete data unit containing the chapter framework scene content and the relationship logic between the two according to the preset structure format. This data unit is the deductive structure data of the structured script data.

[0105] The beneficial effects are that by extracting the standardized chapter skeleton and constructing containers, and by performing precise matching calculations based on the semantic relationship between scenes and chapters and narrative position factors, the final deductive structure data can clearly define the chapter division and scene allocation logic of the plot, giving the plot a clear structural support, ensuring the orderly configuration of subsequent plot development and content expansion, while significantly improving the accuracy of scene and chapter adaptation, and further enhancing the logic and coherence of the plot.

[0106] S4. Based on the plot development requirements in the deductive structure data, configure the plot direction for the chapter container, and derive the control logic from the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data.

[0107] In this embodiment of the invention, the step of configuring plot development requirements for the chapter container based on the plot development needs in the deductive structure data, and deriving the plot development from the preset chapter content template using control logic to obtain the progression control rules of the deductive structure data, includes:

[0108] Extract the state attributes of the chapter containers and the scene definition information from the deductive structure data to obtain the plot development requirement description of the deductive structure data;

[0109] The plot development requirements are matched with the historical plot pattern library to obtain the preliminary plot direction configuration of the deductive structure data;

[0110] Based on the initial plot development configuration, the preset chapter content templates are associated and mapped to obtain the structured narrative templates of the chapter content templates;

[0111] Based on the scene definition information associated with the chapter container, a narrative manifold is constructed on the structured narrative template to obtain the optimized plot direction of the initial plot direction configuration;

[0112] Based on the optimized plot development, the chapter content template is fused according to rules to obtain the control logic of the chapter content template;

[0113] Based on the order of the chapter containers in the deductive structure data, the control logic is integrated by logical link chaining to obtain the advancement control rules of the deductive structure data.

[0114] Extract the state attributes of each chapter container in the deductive structure data. These attributes include information such as the key narrative nodes that have been completed in the current plot progression stage of the chapter, the content direction to be supplemented, etc. At the same time, extract the core content such as scene location, time, background, atmosphere, tone, character interaction, premise, etc. from the scene definition information associated with the chapter container. Systematically integrate these state attributes and scene definition information to sort out the plot progression goals that the chapter needs to achieve, the key information to be conveyed, and the constraints that the scene imposes on the plot, forming a complete descriptive text. This descriptive text is the plot development requirement description of the deductive structure data.

[0115] The historical plot pattern library stores a large number of classic plot development cases of different types of plots. Each case contains corresponding plot development requirement features and a matching plot development framework. The plot development requirement description is semantically compared with the plot development requirement features of all cases in the historical plot pattern library. The plot development framework corresponding to the case with the highest semantic fit is found. The framework is adaptively adjusted to conform to the basic setting of the current plot. The adjusted plot development framework is the initial plot development configuration of the deductive structure data.

[0116] The preset chapter content templates contain a variety of fixed narrative structure frameworks, each corresponding to different plot types and narrative rhythms. Based on the initial plot development, a clear plot type, narrative rhythm, and core nodes are configured. The initial plot development configuration is then matched with the preset chapter content templates to select the most suitable chapter content template. The core narrative structure of this template is retained while redundant parts unrelated to the current plot are removed, forming a template form with a clear structure and logical norms. This template form is the structured narrative template of the chapter content template.

[0117] Retrieve the scene definition information associated with the chapter container, analyze the specific requirements of the scene's atmosphere, tone, spatial characteristics, time background, etc., for the plot presentation, and adjust and optimize the plot node settings, pacing control, conflict design, etc. of the structured narrative template according to these requirements. Add plot details that fit the scene characteristics. For example, if the scene is a rainy night, incorporate the sound of rain and the characters' emotional changes due to the weather into the plot, so that the plot direction is highly consistent with the scene. The optimized plot direction framework is the optimized plot direction of the initial plot direction configuration.

[0118] The core logical sequence of the optimized plot, key turning points, and rules governing character behavior are analyzed and optimized. At the same time, the inherent rules of narrative structure, paragraph division, and expression norms in the chapter content template are extracted. The two types of rules are systematically integrated to clarify the order of plot progression, boundary conditions of character interaction, and logical processes of conflict occurrence and resolution, forming a complete set of rules. This set of rules is the control logic of the chapter content template.

[0119] According to the arrangement order of the chapter containers in the deductive structure data, the control logic corresponding to each chapter container is linked together in the order of plot progression, ensuring that the endpoint of the control logic of the previous chapter is naturally connected to the starting point of the control logic of the next chapter, supplementing the logical rules for the transition between chapters, so that all control logic forms a coherent and complete logical link, which is the progression control rule of the deductive structure data.

[0120] The beneficial effects are that by accurately extracting the needs of plot development and matching them with historical patterns to obtain an initial direction, combining scene information to optimize templates and integrating rules to form control logic, the final integrated advancement control rules can provide a clear basis for plot development, ensuring that the plot direction is highly compatible with the chapter logic of scene needs, guaranteeing the coherence, rationality and relevance of plot development, while improving the efficiency and quality of plot configuration.

[0121] S5. Based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain the realistic dialogue text of the character profile, and the advancement control rules and the chapter content template called by the user are instantiated in a driven manner to obtain the chapter extension data of the structured script data.

[0122] In this embodiment of the invention, based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain realistic dialogue text of the character profile. Then, the advancement control rules and user-invoked chapter content templates are instantiated in a driven manner to obtain chapter extension data of the structured script data, including:

[0123] Based on the scene definition information and plot development associated with the current chapter container in the deductive structure data, context behavior reasoning is performed on the semantic reduction product of the character profile to obtain the character subtext sequence of the structured script data.

[0124] Based on the character's subtext sequence, a dialogue manifold is constructed for the event logic in the plot development to obtain the simulated dialogue text of the structured script data;

[0125] The chapter content template called by the user and the propagation control rules are deconstructed to obtain the driving parameters of the propagation control rules;

[0126] Based on the driving parameters, dynamic content injection is performed on the chapter content template called by the user to obtain the template after the structured script data is filled.

[0127] Based on the state transition path in the propulsion control rules, the narrative logic of the filled template is closed to obtain the preliminary chapter expansion data of the filled template;

[0128] The initial chapter extension data is aligned for context consistency to obtain the chapter extension data of the structured script data.

[0129] Based on the scene definition information associated with the current chapter container in the deductive structure data, including scene location, time, atmosphere, tone, character interaction premises, etc., combined with the core event development path, key turning points and advancement goals with clear plot direction, we focus on the semantic specification products of the character profile, namely the core personality traits and background origins and interaction logic, and analyze the character's behavioral tendencies, thinking patterns and expression demands under this scene and plot. For example, if the scene is a workplace negotiation and the plot is to fight for cooperation rights, a character with the personality traits of being calm and decisive will have the behavioral demand to insist on his position and engage in reasonable bargaining. These inner thoughts of the characters based on the context are organized into a coherent sequence according to the order of event development. This sequence is the character subtext sequence of the structured script data.

[0130] Based on the character's demands and emotional tendencies conveyed by each subtext in the character's subtext sequence, and combined with the event logic in the plot, including key nodes such as causes, development, conflicts, turning points, and endings, the subtext is transformed into colloquial expressions that conform to the character's identity and personality. This ensures that the dialogue content closely matches the event logic. For example, if the subtext is concern about unfair cooperation terms, it is transformed into dialogue that explicitly inquires about the details of the terms. At the same time, the logical order of dialogue between characters is sorted out so that the dialogue can drive the event to develop according to the plot, forming a natural, fluent, and plot-fitting dialogue set. This dialogue set is the simulated dialogue text of the structured script data.

[0131] The chapter content template called by the user is broken down into structural elements, including the introduction, main body, development, and conclusion. At the same time, the pacing control rules are analyzed and the core requirements such as plot progression, rhythm, character interaction constraints, and dialogue duration limits are extracted. These structural elements and core requirements extracted from the template and rules are classified and organized, and the specific execution standards corresponding to each requirement are clarified. These standardized structural elements and core requirements are the driving parameters of the pacing control rules.

[0132] Based on the clearly defined structural element requirements and execution standards in the driving parameters, the simulated dialogue text scene supplements with descriptions of character actions and other relevant content, and injects them precisely into the corresponding positions of the chapter content template called by the user. For example, if the driving parameters require the introductory section to include a scene introduction, then the core content of the scene definition information is filled into the beginning of the template. If the main body development section needs to carry the core dialogue, then the simulated dialogue text is filled into the corresponding sections in logical order, ensuring that the injected content is highly compatible with the template structure and meets the requirements of the driving parameters. The template after injection is the template after the structured script data is filled.

[0133] Extracting the state transition paths from the propagation control rules clarifies the logical relationship of the plot transitioning from one node to another, such as transitioning from the scene introduction state to the conflict outbreak state and then to the negotiation and resolution state. Based on these transition logics, check whether there are logical breaks in the content of the filled template, and supplement necessary transitional descriptions, including character action changes, tone changes, scene connections, etc., so that the content in the template forms a complete narrative logic loop according to the state transition path. For example, supplement the action description of the character's emotional escalation before the conflict breaks out. The template after the logical loop is the preliminary chapter expansion data of the filled template.

[0134] The preliminary chapter expansion data is compared with the content of the preceding and following chapters to check whether the character's personality expression is consistent with the overall setting. For example, a calm character will not suddenly make impulsive statements. The plot development is smoothly connected with the preceding and following chapters. For example, whether the foreshadowing in the previous chapter is echoed in this chapter. Scene elements are consistent. For example, the scene location will not change without reason. Any inconsistencies are corrected and adjusted to ensure that the preliminary chapter expansion data is highly consistent with the context in terms of characters, plot, and scene. The complete data after correction and adjustment is the chapter expansion data of the structured script data.

[0135] The beneficial effects are that by combining scene plots and character profiles to derive realistic dialogues, and by completing template filling and logical closure based on driving parameters and state transition paths, the chapter expansion data formed by contextual consistency alignment not only fits the character settings and plot requirements, but also has complete narrative logic and good contextual coherence. This provides high-quality content support for subsequent structured script data updates and spatiotemporal narrative integration, effectively improving the realism, coherence and overall quality of the plot performance.

[0136] S6. Update the structured script data using the chapter extension data, and perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

[0137] In this embodiment of the invention, the step of updating the structured script data using the chapter extension data and then performing spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data includes:

[0138] Based on the chapter extension data, the structured script data is versioned and supplemented to obtain the updated structured script data.

[0139] Based on the spatiotemporal attributes of the scene in the updated structured script data, the simulated dialogue text is spatiotemporally bound to the context to obtain the spatiotemporally anchored dialogue text.

[0140] Based on the spatiotemporally anchored dialogue text, narrative thread stitching is performed on the updated structured script data to obtain a preliminary narrative fusion of the updated structured script data;

[0141] Narrative topology optimization is performed on the preliminary narrative fusion to obtain the complete narrative structure of the structured script data.

[0142] Based on the realistic dialogue text, scene descriptions, character action prompts, and other content included in the chapter extension data, the original core narrative framework and basic information of the structured script data are preserved. A unique version identifier and update timestamp are marked for the current update operation. The new content in the chapter extension data is accurately added to the corresponding positions in the structured script data according to the order of the chapter containers. Each added part is clearly associated with the corresponding chapter and scene, ensuring that the added content is traceable and does not disrupt the original data logic. The complete data set after the addition is completed is the updated structured script data.

[0143] Extract the spatiotemporal attributes of each scene from the updated structured script data, including specific time points, time spans, scene locations, and spatial layouts. Verify the characters and events corresponding to each dialogue segment in the simulated dialogue text. Bind the dialogue to the scene's temporal attributes to clarify the specific time when the dialogue occurs, and bind it to the scene's spatial attributes to clarify the specific location and character positional relationships. For example, bind a dialogue to a window seat on the third floor of a coffee shop on a rainy night at 8:15 PM, giving each dialogue a clear spatiotemporal background. The bound simulated dialogue text is the spatiotemporally anchored dialogue text of the simulated dialogue text.

[0144] Using the time- and space-anchored dialogue text as a guide, the plot threads of each chapter in the updated structured script data are sorted out, including the main plot and the subplots. Each dialogue is embedded into the corresponding plot thread according to its time and space attributes. The transition descriptions between the dialogue and the preceding and following plots are supplemented to ensure that the dialogue can drive the plot development without logical gaps. For example, the action connection of the characters or the transition of the scene atmosphere are added before and after the dialogue, so that the main plot, subplots and dialogue content are intertwined to form a complete narrative network. This narrative network is the preliminary narrative fusion of the updated structured script data.

[0145] Analyze the narrative structure of the initial narrative fusion, check whether the logical connections between each plot thread are tight, delete repetitive and redundant plot content and dialogue fragments, adjust the pace of plot progression, simplify the description of slow-paced parts, strengthen the presentation of details in key conflict parts, optimize the coherence of character behavior and dialogue, ensure that the introduction, development, transition and conclusion of each chapter are natural and smooth, and at the same time improve the narrative logic loop and fill potential logical loopholes. The optimized complete narrative data is the complete narrative structure of the structured script data.

[0146] The beneficial effects include: accurate updates of structured script data through versioning and supplementation; clear scene positioning for dialogue text through spatiotemporal binding; a coherent plot network constructed by stitching together narrative threads; and improved overall structure and logic through narrative topology optimization. The resulting complete narrative structure possesses a complete narrative framework, coherent plot development, accurate spatiotemporal correspondence, and vivid character dialogue, providing high-quality and complete material for plot performance and significantly improving the presentation effect and execution efficiency of plot performance.

[0147] Example 2

[0148] like Figure 2 As shown in the figure, this embodiment also provides a functional module diagram of a storytelling system.

[0149] The narrative rendering system 100 described in this embodiment can be installed on a terminal. Depending on the functions implemented, the narrative rendering system 100 may include a narrative graph construction module 101, a character profile construction module 102, a narrative structure generation module 103, a logic derivation module 104, a driver-driven instantiation module 105, and a narrative fusion module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the terminal processor and perform fixed functions, stored in the terminal's memory.

[0150] In this embodiment, the functions of each module / unit are as follows:

[0151] The narrative graph construction module 101 is used to perform narrative graph structuring on the initial plot description text to obtain the structured script data of the initial plot description text.

[0152] The character profile construction module 102 is used to semantically reduce the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data.

[0153] The deductive structure generation module 103 is used to construct a chapter container of the structured script data according to the chapter composition logic of the organizational structure in the structured script data, and to allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data.

[0154] The logic derivation module 104 is used to configure the plot direction for the chapter container according to the plot development requirements in the deductive structure data, and to perform control logic derivation between the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data.

[0155] The driven instantiation module 105 is used to perform semantic behavior deduction on the character profile based on the deductive structure data to obtain the realistic dialogue text of the character profile, and to drive-instantiate the advancement control rules and the chapter content template called by the user to obtain the chapter extension data of the structured script data.

[0156] The narrative fusion module 106 is used to update the structured script data using the chapter extension data, and to perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

[0157] In detail, each module in the plot interpretation system 100 described in this embodiment of the invention uses the same technical means as the plot interpretation method described in Embodiment 1 and Embodiment 2, and can produce the same technical effect, which will not be repeated here.

[0158] Example 3

[0159] like Figure 3 As shown, this embodiment also provides a computer terminal, which may include a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may also include a computer program, such as a plot-driven program, stored in the memory 11 and capable of running on the processor 10.

[0160] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the terminal, connecting various components of the terminal via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a storyline program) and calls data stored in the memory 11 to perform various functions of the terminal and process data.

[0161] The memory 11 includes at least one type of medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the terminal, such as the portable hard drive of the terminal. In other embodiments, the memory 11 can also be an external storage device of the terminal, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the terminal. Furthermore, the memory 11 can include both internal storage units and external storage devices. The memory 11 can be used not only to store application software and various types of data installed on the terminal, such as the code of a story-driven program, but also to temporarily store data that has been output or will be output.

[0162] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0163] The communication interface 13 is used for communication between the aforementioned terminal and other terminals, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, Bluetooth interface, etc.), typically used to establish communication connections between the terminal and other terminals. The user interface may be a display, an input unit (such as a keyboard), or optionally, a standard wired or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the terminal and to display a visual user interface.

[0164] The figure only shows a terminal with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the terminal and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0165] For example, although not shown, the terminal may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator, or any other components. The terminal may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0166] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0167] The story-telling program stored in the memory 11 of the terminal is a combination of multiple instructions, which, when run in the processor 10, can achieve the following:

[0168] S1. Perform narrative graph structuring on the initial plot description text to obtain the structured script data of the initial plot description text;

[0169] S2. Semantically reduce the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data;

[0170] S3. Based on the chapter composition logic of the structured script data, construct a chapter container for the structured script data, and allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data.

[0171] S4. Based on the plot development requirements in the deductive structure data, configure the plot direction for the chapter container, and derive the control logic from the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data.

[0172] S5. Based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain the realistic dialogue text of the character profile, and the advancement control rules and the chapter content template called by the user are instantiated in a driven manner to obtain the chapter extension data of the structured script data.

[0173] S6. Update the structured script data using the chapter extension data, and perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

[0174] Specifically, the specific implementation method of the processor 10 for the above instructions can be referred to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, and will not be repeated here.

[0175] Furthermore, if the modules / units integrated into the terminal are implemented as software functional units and sold or used as independent products, they can be stored in a medium. The medium can be volatile or non-volatile. For example, the medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0176] In the several embodiments provided by this invention, it should be understood that the disclosed terminals, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0177] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0178] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0179] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0180] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for storytelling, characterized in that, The method includes: S1. Perform narrative graph structuring on the initial plot description text to obtain the structured script data of the initial plot description text; S2. Semantically reduce the personality and background features of the character definition information in the structured script data to construct the character profile of the structured script data; S3. Based on the chapter composition logic of the structured script data, construct a chapter container for the structured script data, and allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data. S4. Based on the plot development requirements in the deductive structure data, configure the plot direction for the chapter container, and derive the control logic from the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data. S5. Based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain the realistic dialogue text of the character profile, and the advancement control rules and the chapter content template called by the user are instantiated in a driven manner to obtain the chapter extension data of the structured script data. S6. Update the structured script data using the chapter extension data, and perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

2. The plot interpretation method as described in claim 1, characterized in that, The process of structuring the initial plot description text into a narrative graph to obtain structured script data of the initial plot description text includes: Multimodal semantic parsing is performed on the initial plot description text to obtain the first text analysis product of the initial plot description text; Identify the syntactic dependency relationships between lexical items in the first text analysis product, and construct the syntactic dependency relationships in a structured manner to obtain the second text analysis product of the initial plot description text; Using the action descriptors, agent roles, and patient roles in the second text analysis product as nodes and the syntactic dependency relations as edges, an initial narrative graph structure of the initial plot description text is constructed. Semantic role annotation is performed on the nodes in the initial narrative graph structure to obtain the preliminary structured data of the nodes; Logical link closure is performed on the preliminary structured data to obtain the final narrative graph of the initial plot description text; The final narrative graph is serialized and encapsulated to obtain the structured script data of the initial plot description text.

3. The plot interpretation method as described in claim 1, characterized in that, The step of semantically reducing the personality and background features of the character definition information in the structured script data to construct the character profiles of the structured script data includes: Extract the personality trait description text and background trait description text of the character definition information from the structured script data; Based on a pre-defined public personality classification system, the personality trait description text is mapped to a standardized personality tag set, and the standardized personality tag set is integrated through multi-dimensional clustering to generate a personality semantic reduction product of the personality trait description text. Relation topology extraction is performed on the background feature description text to obtain the background semantic reduction product of the background feature description text; The personality semantic reduction product and the background semantic reduction product are semantically fused to obtain the character profile of the structured script data.

4. The plot interpretation method as described in claim 1, characterized in that, The step of constructing a chapter container for the structured script data based on the chapter composition logic of the structured script data, and allocating the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data includes: Based on the narrative unit segmentation rules and hierarchical constraints contained in the structured script data, the chapter skeleton framework of the structured script data is extracted to obtain the logical empty container of the structured script data. Based on the position and context dependency of the logical empty container in the chapter skeleton framework, the logical empty container is bound to a context to obtain the chapter container of the logical empty container; Tensor synthesis is performed on the scene definition information in the structured script data to obtain the scenario feature vector of the scene definition information; The chapter container is vectorized into context to obtain the intent feature vector of the chapter container; The semantic similarity between the context feature vector and the intent feature vector is calculated to obtain the association mapping result of the structured script data. The calculation formula for the association mapping result is as follows: ； In the formula, For the first The scenario definition information and the first The mapping results between chapter containers For the first A scenario feature vector that defines the information of a scenario. For the first The intentional feature vector of each chapter container. This is the transpose of the intention feature vector. For the pre-defined narrative logic weight matrix, For the first The scene definition information and the first The logical distance between the chapter containers in the narrative order The preset position distance penalty coefficient; Based on the association mapping result, the chapter container is synchronized in state, and the synchronized chapter container and the scene definition information are encapsulated in a structure to obtain the deductive structure data of the structured script data.

5. The plot interpretation method as described in claim 1, characterized in that, The step involves configuring plot development requirements for the chapter container based on the plot development needs in the deductive structure data, and deriving the control logic from the plot development and preset chapter content templates to obtain the progression control rules for the deductive structure data, including: Extract the state attributes of the chapter containers and the scene definition information from the deductive structure data to obtain the plot development requirement description of the deductive structure data; The plot development requirements are matched with the historical plot pattern library to obtain the preliminary plot direction configuration of the deductive structure data; Based on the initial plot development configuration, the preset chapter content templates are associated and mapped to obtain the structured narrative templates of the chapter content templates; Based on the scene definition information associated with the chapter container, a narrative manifold is constructed on the structured narrative template to obtain the optimized plot direction of the initial plot direction configuration; Based on the optimized plot development, the chapter content template is fused according to rules to obtain the control logic of the chapter content template; Based on the order of the chapter containers in the deductive structure data, the control logic is integrated by logical link chaining to obtain the advancement control rules of the deductive structure data.

6. The plot interpretation method as described in claim 1, characterized in that, Based on the deductive structure data, semantic behavior inference is performed on the character profile to obtain realistic dialogue text of the character profile. Then, the progression control rules and user-invoked chapter content templates are instantiated in a driven manner to obtain chapter extension data of the structured script data, including: Based on the scene definition information and plot development associated with the current chapter container in the deductive structure data, context behavior reasoning is performed on the semantic reduction product of the character profile to obtain the character subtext sequence of the structured script data. Based on the character's subtext sequence, a dialogue manifold is constructed for the event logic in the plot development to obtain the simulated dialogue text of the structured script data; The chapter content template called by the user and the propagation control rules are deconstructed to obtain the driving parameters of the propagation control rules; Based on the driving parameters, dynamic content injection is performed on the chapter content template called by the user to obtain the template after the structured script data is filled. Based on the state transition path in the propulsion control rules, the narrative logic of the filled template is closed to obtain the preliminary chapter expansion data of the filled template; The initial chapter extension data is aligned for context consistency to obtain the chapter extension data of the structured script data.

7. The plot interpretation method as described in claim 1, characterized in that, The process of updating the structured script data using the chapter extension data and then fusing the updated structured script data with the simulated dialogue text through spatiotemporal narrative fusion to obtain the complete narrative structure of the structured script data includes: Based on the chapter extension data, the structured script data is versioned and supplemented to obtain the updated structured script data. Based on the spatiotemporal attributes of the scene in the updated structured script data, the simulated dialogue text is spatiotemporally bound to the context to obtain the spatiotemporally anchored dialogue text. Based on the spatiotemporally anchored dialogue text, narrative thread stitching is performed on the updated structured script data to obtain a preliminary narrative fusion of the updated structured script data; Narrative topology optimization is performed on the preliminary narrative fusion to obtain the complete narrative structure of the structured script data.

8. A storytelling system, characterized in that, The system for implementing the plot interpretation method according to claim 1 includes: The narrative graph construction module is used to structure the initial plot description text into a narrative graph, thereby obtaining the structured script data of the initial plot description text. The character profile construction module is used to semantically reduce the personality and background features of the character definition information in the structured script data, and construct the character profile of the structured script data. The deductive structure generation module is used to construct a chapter container of the structured script data according to the chapter composition logic of the organizational structure in the structured script data, and to allocate the scene definition information in the structured script data to the chapter container to generate the deductive structure data of the structured script data. The logic derivation module is used to configure the plot direction for the chapter container according to the plot development requirements in the deductive structure data, and to perform control logic derivation between the plot direction and the preset chapter content template to obtain the advancement control rules of the deductive structure data. The driven instantiation module is used to perform semantic behavior deduction on the character profile based on the deductive structure data, obtain the realistic dialogue text of the character profile, and drive the instantiation of the advancement control rules and the chapter content template called by the user to obtain the chapter extension data of the structured script data. The narrative fusion module is used to update the structured script data using the chapter extension data, and to perform spatiotemporal narrative fusion between the updated structured script data and the simulated dialogue text to obtain the complete narrative structure of the structured script data.

9. A terminal, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 7.

Images